# Advancing Shared and Multi-Agent Autonomy in Underwater Missions: Integrating Knowledge Graphs and Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2507.20370 · HTML: https://mlsanity.com/paper/2507.20370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 12 of 12)

- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [Behavior Trees in Robotics and AI: An Introduction](https://mlsanity.com/paper/1709.00084/) (2017)
- [Enhancing Retrieval-Augmented Generation: A Study of Best Practices](https://mlsanity.com/paper/2501.07391/) (2025)
- [Towards Blended Reactive Planning and Acting using Behavior Trees](https://mlsanity.com/paper/1611.00230/) (2016)
- [Stonefish: Supporting Machine Learning Research in Marine Robotics](https://mlsanity.com/paper/2502.11887/) (2025)
- [Investigation of the Challenges of Underwater-Visual-Monocular-SLAM](https://mlsanity.com/paper/2306.08738/) (2023)
- [From market-ready ROVs to low-cost AUVs](https://mlsanity.com/paper/2108.05792/) (2021)
- [Underwater Robotic Simulators Review for Autonomous System Development](https://mlsanity.com/paper/2504.06245/) (2025)
- [Digital Twins Below the Surface: Enhancing Underwater Teleoperation](https://mlsanity.com/paper/2402.07556/) (2024)
- [Current Advancements on Autonomous Mission Planning and Management Systems: an AUV and UAV perspective](https://mlsanity.com/paper/2007.05179/) (2020)
- [Real-time Seafloor Segmentation and Mapping](https://mlsanity.com/paper/2504.10750/) (2025)

## Abstract (arXiv)

Robotic platforms have become essential for marine operations by providing regular and continuous access to offshore assets, such as underwater infrastructure inspection, environmental monitoring, and resource exploration. However, the complex and dynamic nature of underwater environments, characterized by limited visibility, unpredictable currents, and communication constraints, presents significant challenges that demand advanced autonomy while ensuring operator trust and oversight. Central to addressing these challenges are knowledge representation and reasoning techniques, particularly knowledge graphs and retrieval-augmented generation (RAG) systems, that enable robots to efficiently structure, retrieve, and interpret complex environmental data. These capabilities empower robotic agents to reason, adapt, and respond effectively to changing conditions. The primary goal of this work is to demonstrate both multi-agent autonomy and shared autonomy, where multiple robotic agents operate independently while remaining connected to a human supervisor. We show how a RAG-powered large language model, augmented with knowledge graph data and domain taxonomy, enables autonomous multi-agent decision-making and facilitates seamless human-robot interaction, resulting in 100% mission validation and behavior completeness. Finally, ablation studies reveal that without structured knowledge from the graph and/or taxonomy, the LLM is prone to hallucinations, which can compromise decision quality.